The Effect of Cognitive Function Health Care Using Artificial Intelligence Robots for Older Adults: Systematic Review and Meta-analysis
Bibliographic record
Abstract
BACKGROUND: With rapidly aging populations in most parts of the world, it is only natural that the need for caregivers for older adults is going to increase in the near future. Therefore, most technologically proficient countries are in the process of using artificial intelligence (AI) to build socially assistive robots (SAR) to play the role of caregivers in enhancing interaction and social participation among older adults. OBJECTIVE: This study aimed to examine the effect of intervention through AI SAR on the cognitive function of older adults through a systematic literature review. METHODS: We conducted a meta-analysis of the various existing studies on the effect of AI SAR on the cognitive function of older adults to standardize the results and clarify the effect of each method and indicator. Cochrane collaboration and the systematic literature review flow of PRISMA (Preferred Reporting Item Systematic Reviews and Meta-Analyses) were used on original, peer-reviewed studies published from January 2010 to March 2022. The search words were derived by combining keywords including Population, Intervention, and Outcome-according to the Population, Intervention, Comparison, Outcome, Time, Setting, and Study Design principle-for the question "What is the effect of AI SAR on the cognitive function of older adults in comparison with a control group?" (Population: adults aged ≥65 years; Intervention: AI SAR; Comparison: comparison group; Outcome: popular function; and Study Design: prospective study). For any study, if one condition among subjects, intervention, comparison, or study design was different from those indicated, the study was excluded from the literature review. RESULTS: In total, 9 studies were selected (6 randomized controlled trials and 3 quasi-experimental design studies) for the meta-analysis. Publication bias was examined using the contour-enhanced funnel plot method to confirm the reliability and validity of the 9 studies. The meta-analysis revealed that the average effect size of AI SAR was shown to be Hedges g=0.43 (95% CI -0.04 to 0.90), indicating that AI SAR are effective in reducing the Mini Mental State Examination scale, which reflects cognitive function. CONCLUSIONS: The 9 studies that were analyzed used SAR in the form of animals, robots, and humans. Among them, AI SAR in anthropomorphic form were able to improve cognitive function more effectively. The development and expansion of AI SAR programs to various functions including health notification, play therapy, counseling service, conversation, and dementia prevention programs are expected to improve the quality of care for older adults and prevent the overload of caregivers. AI SAR can be considered a representative, digital, and social prescription program and a nonpharmacological intervention program that communicates with older adults 24 hours a day. Despite its effectiveness, ethical issues, the digital literacy needs of older adults, social awareness and reliability, and technological advancement pose challenges in implementing AI SAR. Future research should include bigger sample sizes, pre-post studies, as well as studies using an older adult control group.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.017 | 0.049 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.019 | 0.036 |
| Bibliometrics | 0.007 | 0.007 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".